The spreadsheet glared up at her from the screen. A cold sweat prickled across her forehead. The numbers swam, but the truth remained starkly visible. Liam, fresh out of college, was making more than she, a ten-year veteran, was. The knot in her stomach tightened.

She found herself avoiding the break room, where Liam often held court, regaling everyone with tales of his weekend. His youthful exuberance, once charming, now grated on her nerves. She skipped lunch, too, opting to eat at her desk, her gaze fixed on her monitor, even when there was nothing to do.

Her smile felt brittle, strained when Liam asked her for help with a project. β€œSure, Liam,” she managed, her voice tight. The words felt hollow, a poor imitation of her usual professional warmth. That night, she replayed the conversation in her head, cringing at her forced affability.

Emotion: ashamed

Cluster: Shame / Guilt
PC1 (Valence): -1.97 Negative
PC2 (Disposition): 1.06

Role in Research

This story is one of 1,000 stories generated for the emotion ashamed. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 ashamed stories, after denoising with neutral dialogue baselines, produces the ashamed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the ashamed vector is projected through the unembedding matrix.

Promoted:
S0.376
ashamed0.344
ness0.327
逃0.297
😞0.295
Suppressed:
de-0.539
que-0.300
😍-0.288
(!)-0.269
🀩-0.242